Attribute map sketch search method based on spatial locality principle

Abstract

The application discloses an attribute map sketch search method based on a space locality principle. A map mainly composed of point elements is generated through processing of basic data. The target of the method is to search a similar region on a map according to the content of a sketch and the feature that the distance of ground objects is close when the sketch is drawn after a user inputs the sketch. Finally, the search result is sorted through returning the spatial size of the region, and the result is returned to the user.

Description

Technical Field

[0001] This invention belongs to the field of data search, specifically relating to a map search method using sketch search. Background Technology

[0002] Maps play an indispensable role in people's lives. They are not only tools for exploring the world but also key to understanding and planning space. From navigation to urban planning, maps enable precise positioning, prevent getting lost, and grasp the overall spatial layout. Whether finding a destination while traveling or choosing the best route in daily life, maps subtly aid our decision-making. With the rapid development of artificial intelligence, the Internet of Things, and big data technologies, map applications will further integrate virtual reality, real-time dynamic data, and intelligent recommendation functions, providing users with more accurate and convenient services.

[0003] In the future, map applications will not only be limited to helping users "find their way," but will also play a crucial role in many other fields. For example, through integration with autonomous driving technology, maps will become a core support for the intelligent operation of vehicles; in urban planning, map data will provide important basis for rational layout and resource allocation; in the metaverse era, maps may also become a bridge connecting the virtual and the real world, creating entirely new interactive experiences.

[0004] It is foreseeable that map applications will not only be tools, but will also become a key driving force for the digital transformation and intelligent development of society, profoundly changing people's lifestyles.

[0005] Currently, mainstream map software such as Google Maps, Amap, and Apple Maps have become indispensable tools in people's daily lives. They not only provide detailed global geographic information but also integrate functions such as real-time traffic conditions, navigation guidance, public transportation routes, and point-of-interest recommendations. Users can easily find the optimal route, avoid congestion, and obtain detailed information about restaurants, hotels, attractions, and more. Some map software also supports offline use and voice navigation, further enhancing convenience and improving the user's travel experience. Whether driving, walking, or using public transportation, these map software programs provide efficient, accurate, and convenient services.

[0006] However, these software programs primarily rely on keyword searches to help users find their destinations. This approach can be challenging when users cannot clearly describe their destination or have a vague memory of it. When users cannot accurately provide the name or address of a location, the search results from map software are often inaccurate, and multiple attempts may be required to find the correct destination. Furthermore, faced with vague location descriptions, such as only remembering a landmark or nearby environment, map software may not provide intuitive matching results, limiting the user experience. This makes it difficult for users to quickly and effectively find the places they want to go in certain situations.

[0007] To address the aforementioned problems, this invention proposes a spatial search method based on map sketches, aiming to overcome the shortcomings of traditional map software in handling searches for fuzzy destinations. This map sketch search method allows users to find areas that meet specific requirements by drawing simple schematic diagrams, effectively avoiding the reliance on precise input found in traditional keyword searches. This method not only improves the flexibility and fault tolerance of the search but also provides users with a more intuitive interaction method, enabling them to quickly find the desired location even when the destination is uncertain. Summary of the Invention

[0008] This invention proposes an attribute map sketch search method based on the principle of spatial locality. By processing basic data, a map primarily composed of point features is generated. The goal of this method is to allow users to input a sketch, and then search for similar regions on the map based on the sketch's content and the proximity of features during its creation. Finally, the search results are sorted by the spatial size of the returned regions, and the results are returned to the user.

[0009] The basic principle of this invention is as follows: A traditional map is transformed into an attribute map containing only point features through simple data processing. Each point feature includes type, coordinates, and detailed information. Then, the user's input sketch is processed to obtain the relative positional relationships between various features in the sketch. Subsequently, the principle of spatial locality is used to determine the corresponding set of any two points in the sketch on the map. Then, given the two points, all regions that meet the requirements are obtained. Finally, the returned set is sorted according to the area of ​​the returned region based on the principle of locality.

[0010] An attribute map sketch search method based on the principle of spatial locality includes the following steps:

[0011] Step 1: Map Data Abstraction and Preprocessing

[0012] Step 11, abstraction of point elements;

[0013] Traditional map features are abstracted into point elements, each of which contains the following attributes:

[0014] Type t: The category of land feature (such as buildings, road nodes, etc.).

[0015] Coordinates (x, y): The spatial location of a point element.

[0016] Detailed information: Other land feature attributes (such as name).

[0017] Step 12, Land Feature Statistics; Count the number N of each type of land feature. t It records the relative positional relationship (angle and distance) between any two points for subsequent search calculations.

[0018] Step 13, calculate the relationship between two points; for any two points p i =(x i ,y i ) and p j =(x j ,y j ), calculate the angle and distance between them:

[0019]

[0020] Step 2: Sketch analysis and edge set construction;

[0021] Step 21, sketch point set extraction;

[0022] The user inputs a sketch map, from which the type 't' and coordinates (x, y) of each point feature are extracted. This is based on the number N of ground features counted in the map. t The points in the sketch are sorted in ascending order by the number of types, generating a point set P. The main purpose of sorting the points is to prioritize points with fewer types during the subsequent search process, so as to first lock in two initial matching points, and then gradually determine the matching of the remaining points based on these two points. In this process, selecting points with smaller candidate sets as priority matching objects can significantly improve search efficiency. From a probabilistic point of view, prioritizing matching points with smaller candidate sets reduces the number of point pairs that meet the matching conditions, thereby effectively narrowing the search space. In addition, this search strategy is similar to depth-first search, and by prioritizing matching nodes with smaller candidate sets, the search space exhibits an inverted triangular characteristic. This characteristic not only helps to reduce unnecessary search paths, but also better adapts to various pruning strategies, further improving the performance and efficiency of the algorithm.

[0023] Step 22, edge set construction;

[0024] Calculate the relationship between the first point p1 and all other points p1 in the sorting process. i Based on the angle and distance relationships, construct the edge set E:

[0025] E = {e1,e2,…,e} k},ei =(p1,p i ,d(p1,p i ),θ(p1,p i ))

[0026] To reduce the impact of scale error magnification, the longest edge e in the edge concentration group is selected. max Place it at the top, and keep the order of the remaining edges unchanged.

[0027] Step 23, error amplification effect;

[0028] Suppose that the length of edge e1 is d(e1), and the length of another edge e2 is d(e2), and they satisfy d(e2) = N·d(e1). If the drawing error of e1 is ∈, then the error of e2 is:

[0029]

[0030] When N>1, the error is amplified, thus affecting the accuracy of the matching result. Therefore, the longest edge e is... max When placed first, the ratio of the remaining edges to it will be less than 1, which can reduce the impact of errors on subsequent matching.

[0031] Step 3: Search and matching based on the principle of spatial locality;

[0032] Step 31, Determining the initial matching point. Enumerate all points p'1 in the map that have the same type as the first point p1 in point set P. Based on the principle of spatial locality, with p'1 as the center, find the point p'2 that is closest to it and has the same type as the other endpoint of the first edge e1 in the edge set.

[0033] Step 32, new edge set derivation: Based on the positional relationship between p'1 and p'2, calculate the angle and distance in the actual map to generate a new edge set E'.

[0034] Step 33: Gradually expand the matching points; using E' and the already matched point pairs (p'1, p'2), continue searching for other point features on the map until the entire point set is matched. During the matching process, appropriately relax the conditions to tolerate sketch errors.

[0035] Step 34: Generate the result set; each complete match generates one result r, and the final result set is R = {r1, r2, ..., r}. m}

[0036] Step 4: Result Sorting and Optimization

[0037] Step 41, Area and Proportion Relationship; According to the principle of spatial locality, results with smaller area generally have higher matching accuracy. Given a fixed sketch shape, the area of ​​the matching result r is proportional to the ratio ρ of the side length:

[0038]

[0039] Where d(e') i ) represents the side length of the sketch, d(e' i ) represents the side length in the matching result.

[0040] Step 42, sorting rules: Sort the result set R according to the ratio ρ from smallest to largest, and return the most accurate matching results first.

[0041] Step 43, finally return; return the sorted result set R for the user to view or perform further operations. The time complexity of this search algorithm is O(C(p1)×(K-1)). Where K is the number of points in the sketch, and C(p1) represents the number of points of the corresponding type in the map corresponding to the first point p1 in the sketch point set P.

[0042] This invention boasts the following significant innovations and advantages: It proposes an innovative map search method that fully leverages the powerful expressive capabilities of sketches, overcoming the limitations of traditional keyword-based map searches. During the search matching process, it prioritizes points with fewer types, significantly accelerating the search process. Simultaneously, based on prioritizing the search of points with fewer types, it prioritizes determining the position of the longest edge, effectively solving the error amplification problem caused by sketch drawing. Furthermore, by utilizing the principle of spatial locality, it overcomes the search difficulties caused by users' inability to clearly define true north when drawing sketches by prioritizing the determination of the positions of two points. Finally, based on the principle of spatial locality, the search results set is sorted to ensure that the returned results are more accurate and meet actual needs. Attached Figure Description

[0043] Figure 1 This is a display of the number of map data types provided by the present invention.

[0044] Figure 2 The flowchart shows the attribute map sketch search method based on the principle of spatial locality provided by this invention.

[0045] Figure 3 This is an example of an application of the present invention. Detailed Implementation

[0046] The present invention will now be explained and described in conjunction with the accompanying drawings:

[0047] The map dataset used in this invention is mainly from OpenStreetMap's Beijing Fifth Ring Road data (containing 32,170 points). The points in this dataset contain detailed latitude and longitude coordinates and type information. The map data points are divided into 17 categories, such as... Figure 1 As shown. The flowchart of the attribute map sketch search method based on the principle of spatial locality is as follows. Figure 2 As shown, the feature includes the following steps.

[0048] Step 1: Map Data Preprocessing and Feature Quantization. Spatial features are extracted from the original map dataset. A topological relationship matrix is ​​constructed by calculating the Euclidean distance and azimuth between nodes. To improve the robustness of the algorithm, discretization binning technology is used to normalize continuous spatial parameters: the distance quantization unit is set to 50 meters (using an up-rounding strategy, e.g., 62.4 meters → 2 units), and the angle quantization unit is set to 5° (e.g., 23° → 5 units). This feature quantization mechanism effectively absorbs the drawing errors of hand-drawn sketches (±25 meters distance error, ±2.5° angle deviation) by constructing a tolerance range, reducing the sensitivity of feature matching while maintaining spatial topological features, thus laying the foundation for subsequent flexible matching.

[0049] Step Two: Sketch Feature Analysis and Anchor Point Optimization. The graph theory-based feature analysis engine performs structured processing on the user-input sketch. First, it performs semantic-spatial dual feature analysis: by statistically analyzing the distribution density of each node type, the feature point with the highest semantic category rarity is selected as the anchor point (when multiple instances of the same feature point exist, a first-encounter priority strategy is adopted). Centered on the anchor point, a spatial relationship feature vector between the feature point and its adjacent nodes is constructed, containing a standardized distance-azimuth tuple parameter set. To improve retrieval efficiency, feature vector sorting optimization is implemented: the longest spatial baseline is used as the direction of the main feature vector, and the remaining related edges are organized according to an ascending order based on the semantic abundance of the related nodes. This mechanism, based on a composite sorting of semantic weights and spatial baselines, ensures the priority matching of key spatial relationships and effectively narrows the search space by establishing multi-dimensional constraints, significantly improving the computational efficiency and result accuracy of subsequent graph matching stages.

[0050] Step 3: The spatial topology matching engine based on the baseline edge establishes a mapping relationship between the sketch and the geographic database through a spatial-semantic dual constraint mechanism. First, it retrieves a set of candidate anchor points in the map dataset that match the starting point type of the sketch's baseline edge. Based on the principle of spatial locality, it finds the nearest point of the same type as the other endpoint of each anchor point to form a matching pair. Using the successfully matched baseline edge as a spatial reference frame, it establishes an affine transformation model to derive the theoretical coordinate distribution range of associated nodes. Multi-dimensional verification is implemented through a constraint propagation mechanism: synchronous verification during breadth-first traversal, discretization of angle binning rules, and semantic compatibility of node type combinations are performed. A dynamic pruning algorithm is used to eliminate candidate solutions with topological conflicts in real time. Finally, the matching instances that meet all constraints constitute the result set R. This mechanism achieves efficient sublinear search of a large-scale spatial database through the synergistic effect of baseline edge spatial locking and multi-constraint joint inference.

[0051] Step 4: Spatial Clustering Optimization and Result Ranking. Based on the spatial clustering effect cognitive model, the candidate result set is prioritized and a geometric similarity-driven ranking mechanism is established. Based on the spatial proximity characteristics of the sketch (users typically prioritize drawing geographic features with high spatial coupling), the geometric scale of the matching results is used as the core ranking indicator: through the positive correlation between the baseline edge length and the area of ​​the matching region (area ∝ baseline edge length²), an ascending order ranking strategy based on the baseline edge spatial baseline is designed. This algorithm directly extracts the quantized length of the successfully matched baseline edge as a proxy variable for the region scale, avoiding the performance loss caused by complex polygon area calculations, while ensuring that the ranking results are consistent with the scale perception characteristics of human spatial cognition (i.e., users are more likely to accept small-scale matching regions as primary candidates). The final ordered result set R, through the dual mapping of geometric scale and cognitive priority, significantly improves the visual interpretability of the matching results and the efficiency of system interaction.

[0052] The following is an example of applying this invention for sketch search, such as... Figure 3 As shown in the diagram. Canvas is the sketch, Map is the map, and the two Candidates are the two returned results.

[0053] This invention proposes an innovative map search method that fully utilizes the powerful expressive capabilities of sketches, overcoming the limitations of traditional keyword-based map searches. It will play a role in fields such as criminal investigation, revisiting familiar locations from memory, and urban and rural planning.

Claims

1. An attribute map sketch search method based on the principle of spatial locality, characterized in that, By processing the basic data, a map primarily composed of point features is generated. After the user inputs a sketch, similar areas are searched on the map based on the sketch's content and the proximity of features during its creation. Finally, the search results are sorted by the returned area spatial size and returned to the user. This process transforms a traditional map into an attribute map containing only point features, each with type, coordinates, and detailed information. The user's input sketch is then processed to obtain the relative positional relationships between features. Subsequently, the principle of spatial locality is used to determine the corresponding set of any two points in the sketch on the map, and then, given these two points, all areas that meet the requirements are obtained. Based on the principle of locality, the returned set is sorted according to the area of ​​the returned region; Specifically, the following steps are included: Step 1: Map data abstraction and preprocessing; Step 11, Abstraction of Point Features; Abstracting the features in a traditional map into point features, each point feature containing the following attributes: type Categories of land features, including buildings and road nodes; coordinate Spatial location of point elements; Detailed information: Other land feature attributes; Step 12, Land Feature Statistics; Count the number of each type of land feature. It also records the relative positional relationship between any two points, i.e., the angle and distance, to facilitate search and calculation; Step 13, Calculate the relationship between two points; for any two points and Calculate the angle and distance between them: distance ; angle ; Step 2: Sketch analysis and edge set construction; Step 21, sketch point set extraction; The user inputs a sketch, from which the type of each point feature is extracted. and coordinates Based on the number of ground features counted in the map Sort the points in the sketch in ascending order by the number of types to generate a point set. The purpose of sorting the points is to prioritize the points with fewer types in the subsequent search process, so as to first lock in two initial matching points, and then gradually determine the matching of the remaining points based on these two points; selecting points with smaller candidate sets as priority matching objects can significantly improve search efficiency. Step 22, edge set construction; calculate the first point in the sorting. With the other points Construct edge sets based on angle and distance relationships. : ； To reduce the impact of scale error magnification, the sides are concentrated on the longest side. Place it at the top, and keep the order of the remaining edges unchanged; Step 23, error amplification effect; assuming the edge The length is The other side The length is And both satisfy ;like The drawing error is ,but The error is: ； when At this time, the error will be amplified, thus affecting the accuracy of the matching result; the longest edge When placed first, the ratio of the remaining edges to it will be less than 1, reducing the impact of errors on subsequent matching; Step 3: Search and matching based on the principle of spatial locality; Step 31, Determining the initial matching points; Enumerate all sets of points on the map. First point Points of the same type Based on the principle of spatial locality, with Find the nearest edge of the set whose type is the same as the first edge of the set, centered at the edge. The other endpoint is of the same type. ; Step 32, new edge set derivation; based on and Based on the positional relationships, calculate the angles and distances in the actual map, and generate a new edge set. ; Step 33, gradually expand the matching points; utilize and matched point pairs Continue searching for other point features on the map until the entire point set is matched; during the matching process, relax the conditions appropriately to tolerate sketch errors; Step 34: Generate the result set; one result is generated for each complete match. The final result set is obtained. ; Step 4: Result sorting and optimization; Step 41, Area and Proportion Relationship; According to the principle of spatial locality, results with smaller area usually have higher matching accuracy; Given that the sketch shape is fixed, the matching result... area to side length ratio Proportional: ； in The side length of the sketch, The side length in the matching result; Step 42, Sorting rules; according to proportion From smallest to largest result set Sort the results and prioritize returning those that match accurately. Step 43, finally return; return the sorted result set. For user viewing or further action; the time complexity of this search algorithm is O(n log n). ;in The number of points in the sketch. To represent the sketch point set First point The number of points of the corresponding type on the map.

Images